© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8764
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     інших
    -1.09
    ☆☆☆☆
    -1.08
     vanille
    -1.06
    橈
    -1.05
     letzte
    -1.03
    amerikanischer
    -1.03
    べた
    -1.03
    teht
    -1.02
    uré
    -1.02
    stant
    -1.02
    POSITIVE LOGITS
     then
    1.46
     its
    1.30
     if
    1.27
     including
    1.26
     you
    1.23
     using
    1.20
     before
    1.16
     greatly
    1.16
     now
    1.14
     ensure
    1.10
    Activations Density 0.132%

    No Known Activations